huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 04:14:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Remove outdated TODO

Browse Source
This commit is contained in:
Daniël de Kok 2025-02-07 20:13:50 +00:00
parent df582a1842
commit fc3ac8075b
1 changed files with 0 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
server/text_generation_server/layers/fp8.py
View File

@ -23,7 +23,6 @@ else:
quantization = None quantization = None
try: try:
# TODO: needs to be ported over to MoE and used on CUDA.
from moe_kernels.fp8_utils import w8a8_block_fp8_matmul, per_token_group_quant_fp8 from moe_kernels.fp8_utils import w8a8_block_fp8_matmul, per_token_group_quant_fp8
except ImportError: except ImportError:
w8a8_block_fp8_matmul = None w8a8_block_fp8_matmul = None